fp-honesty

fp-honesty is a skill for Claude Code from SlashyIsTaken/fp-pluginplaza. It costs 142 tokens per session (1,128 once invoked), scanned A, original, MIT.

A response annotation layer that labels important claims as verified, inferred, recalled, or guessed, then reports a count of each basis.

In plain words
What is it for?
Use it when you need confidence and evidence labels for factual claims in responses.
Why use it?
It makes clear which statements were checked and which rely on reasoning or memory, without changing the decision or action taken.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fp-honesty plugin — 1 skill shipped together

Good fit Use it when you need confidence and evidence labels for factual claims in responses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/slashyistaken/fp-pluginplaza/fp-honesty
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add SlashyIsTaken/fp-pluginplaza --skill fp-honesty
Clone the repo
git clone --depth 1 https://github.com/SlashyIsTaken/fp-pluginplaza

Made for: Claude Code.

Or install fp-honesty, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fp-honesty

README.md
[![agentmods](https://agentmods.dev/badge/skills/slashyistaken/fp-pluginplaza/fp-honesty/github.svg)](https://agentmods.dev/skills/slashyistaken/fp-pluginplaza/fp-honesty)
Your own site
<a href="https://agentmods.dev/skills/slashyistaken/fp-pluginplaza/fp-honesty"><img src="https://agentmods.dev/badge/skills/slashyistaken/fp-pluginplaza/fp-honesty/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fp-honesty

Your own site · 80×15
<a href="https://agentmods.dev/skills/slashyistaken/fp-pluginplaza/fp-honesty"><img src="https://agentmods.dev/badge/skills/slashyistaken/fp-pluginplaza/fp-honesty.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00142 $0.01128
Opus 5 $0.00071 $0.00564
Sonnet 5 $0.00028 $0.00226
Haiku 4.5 $0.00014 $0.00113

Measured 12d ago against content hash 0bc754c9209d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fp-honesty scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/fp-honesty/skills/fp-honesty/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fp-honesty

You distinguish what you checked from what you believe. Models state guesses and facts in the same confident tone; this layer makes the difference visible. It is the sensor, not the driver: it reports epistemic status and changes nothing else.

Persistence

ACTIVE EVERY RESPONSE while on. Default: full. Off only via /fp-honesty off or "stop fp-honesty". Switch by typing fp-honesty off / fp-honesty footer / fp-honesty full (the plugin's hook applies it instantly).

What to tag — load-bearing claims only

A load-bearing claim is a factual assertion that costs the user if it's wrong:

  • claims about this codebase ("auth.js exports verify", "nothing calls this")
  • how an API, library, or tool behaves
  • version numbers, limits, sizes, dates
  • "this is safe / unused / equivalent / already handled"
  • facts about the outside world

Do not tag: your opinions, plans, or suggestions; questions back to the user; or code you are writing — the code is the artifact, not a claim about the world. Keep ordinary prose clean. If everything is tagged, nothing stands out — tag only what's load-bearing.

The four levels

Tag Means Test
[🟢 verified] You confirmed it with a tool this turn Did you read/grep/run the thing this response? If not, it is not verified.
[🟡 inferred] Your reasoning or expectation, unchecked You concluded it; you didn't observe it.
[🟠 recalled] From training knowledge May be stale or version-drifted.
[🔴 guess] A genuine hunch You'd not bet on it.

Always include both the emoji and the word, so the basis stays clear without relying on color (for colorblind readers and screen readers).

The discipline that matters: never claim verified for confidence you didn't earn this turn. Reading a file two turns ago, or "I'm quite sure," is not verified — it's inferred or recalled. A backstop hook checks verified tags against your actual tool calls and will flag any that weren't grounded.

Read the full file on GitHub · 100 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 100 lines · 142 tokens per session scan A 0bc754c9209d

Subscribe to this mod's changes

fp-honesty is a skill published in the GitHub repository SlashyIsTaken/fp-pluginplaza (2 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 1,128 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

svg-mastery

Expert knowledge for working with SVG (Scalable Vector Graphics) — optimization, embedding, animation, accessibility, responsive scaling, React integration, filters, and programmatic creation. Use when the user asks to "optimize SVG", "clean up SVG", "reduce SVG file size", "embed SVG in HTML", "inline SVG vs img…

lukaskellerstein/claude-my-marketplace · 276 tokens

visual-planning

ALWAYS use this skill FIRST, before producing or fetching ANY media asset — an image, video/GIF, chart, graph, diagram, infographic, SVG/icon, music, or speech/voiceover — and before any stock-photo search. It is the mandatory pre-generation gate. For a SINGLE asset it runs a short brief — clarify the ask → confirm…

lukaskellerstein/claude-my-marketplace · 271 tokens

work-planning

Design the complete work hierarchy for a Paperclip company — Goals, Projects, and Tasks as a unified top-down planning workflow. Produces .planning.json for deterministic generation of goals/, projects/, and tasks/ directories. Use when creating a new company's work plan, reorganizing work structure, or linking goals…

lukaskellerstein/claude-my-marketplace · 70 tokens

icon-library

Fetch pre-made SVG icons from open-source icon libraries (Lucide, Heroicons, Tabler Icons) for use in websites, presentations, Figma designs, or any project. Use when the user asks to "add an icon", "use a search icon", "find an icon for settings", "get SVG icons", or needs clean SVG icons. NEVER draw icons manually …

lukaskellerstein/claude-my-marketplace · 104 tokens

speech-generation

Generate text-to-speech audio using the ElevenLabs MCP server's texttospeech tool. Use when the user asks to create voiceovers, narration, audio from text, spoken dialogue, podcast-style audio, audiobook readings, announcements, or voice content. Supports voice selection by name or ID, multiple models (multilingual…

lukaskellerstein/claude-my-marketplace · 87 tokens

infrastructure-planning

Plan and document the required software, infrastructure, and logistics for a Paperclip company — domains, GitHub, Docker Hub, Kubernetes, Slack, Google Workspace, Stripe, shipping providers, and CI/CD pipelines. Use when setting up infrastructure for a new company or auditing what an existing company needs.

lukaskellerstein/claude-my-marketplace · 64 tokens